Preprint · 2026 · Open access
$\textbf{Re}^{2}$: Unlocking LLM Reasoning via Reinforcement Learning with Re-solving
arXiv (Cornell University) · Published 7 March 2026 · DOI 10.48550/arxiv.2603.07197
In brief
“$\textbf{Re}^{2}$: Unlocking LLM Reasoning via Reinforcement Learning with Re-solving” is a 2026 preprint by Pinzheng Wang and 6 co-authors, published in arXiv (Cornell University). OpenAlex counts 4 citations as of 15 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 4
- Most cited in
- 2026 (4)
- References
- 34
- Authors
- 7
Abstract
Reinforcement learning with verifiable rewards (RLVR) has shown promise in enhancing the reasoning performance of large language models (LLMs) by increasing test-time compute. However, even after extensive RLVR training, such models still tend to generate unnecessary and low-quality steps in their chain-of-thought (CoT), leading to inefficient overthinking and lower answer quality. We show that when the initial direction or quality of the CoT is suboptimal, the model often fails to reach the correct answer, even after generating several times more tokens than when the initial CoT is well-initialized. To this end, we introduce Reinforcement Learning with Re-solving (Re$^2$), in which LLMs learn to flexibly abandon unproductive reasoning paths and restart the solution process when necessary, rather than always committing to a final answer. Re$^2$ applies pure reinforcement learning without any preliminary supervised fine-tuning, successfully amplifying the rare redo behavior in vanilla models from only 0.5% to over 30%. This leads to substantial performance gains over standard RLVR under the same training compute budget, and also demonstrates notable improvements in test-time performance as the number of samples increases.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Wang, P., Xu, S., Li, J., Luo, Y., Li, D., Hao, J., & Zhang, M. (2026). $\textbf{Re}^{2}$: Unlocking LLM Reasoning via Reinforcement Learning with Re-solving. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2603.07197
MLA 9
Wang, Pinzheng, et al. “$\textbf{Re}^{2}$: Unlocking LLM Reasoning via Reinforcement Learning with Re-solving.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2603.07197.
Chicago
Wang, Pinzheng, Shuli Xu, Juntao Li, Yu Luo, Dong Li, Jianye Hao, and Min Zhang. 2026. “$\textbf{Re}^{2}$: Unlocking LLM Reasoning via Reinforcement Learning with Re-solving.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2603.07197.
Harvard
Wang, P. et al. (2026) ‘$\textbf{Re}^{2}$: Unlocking LLM Reasoning via Reinforcement Learning with Re-solving’, arXiv (Cornell University). doi:10.48550/arxiv.2603.07197.
IEEE
P. Wang et al., “$\textbf{Re}^{2}$: Unlocking LLM Reasoning via Reinforcement Learning with Re-solving,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2603.07197.
BibTeX
@misc{wang2026textbf,
title = {{\$\textbf{Re}^{2}\$: Unlocking LLM Reasoning via Reinforcement Learning with Re-solving}},
author = {Wang, Pinzheng and Xu, Shuli and Li, Juntao and Luo, Yu and Li, Dong and Hao, Jianye and Zhang, Min},
howpublished = {arXiv (Cornell University)},
year = {2026},
doi = {10.48550/arxiv.2603.07197},
url = {https://doi.org/10.48550/arxiv.2603.07197}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- large language models
- chain-of-thought reasoning
- reinforcement learning with verifiable rewards
- overthinking
- test-time compute
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Wang, P., Xu, S., Li, J., Luo, Y., Li, D., Hao, J., & Zhang, M. (2026). $\textbf{Re}^{2}$: Unlocking LLM Reasoning via Reinforcement Learning with Re-solving. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2603.07197
How many times has this paper been cited?
4 times, according to OpenAlex on 15 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access: read the free full text at arXiv (Cornell University).
Who wrote this paper?
Pinzheng Wang, Shuli Xu, Juntao Li, Yu Luo, Dong Li, Jianye Hao, Min Zhang.
What is the DOI of this paper?
10.48550/arxiv.2603.07197. The permanent link is https://doi.org/10.48550/arxiv.2603.07197.
Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.